© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47293
    Prev
    Next
    INDEX
    Explanations

    rainbows and colorful skies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è®°äºĭ
    -0.07
     metro
    -0.07
    享åıĹ
    -0.06
    åŁ¹åħ»
    -0.06
    åĬ¡å®ŀ
    -0.06
    éĩİå¿ĥ
    -0.06
    éĩİèĽ®
    -0.06
     rat
    -0.06
    ano
    -0.06
     Metro
    -0.06
    POSITIVE LOGITS
    ledi
    0.08
    dap
    0.08
    orderBy
    0.08
    覧
    0.08
    AFX
    0.08
     Auss
    0.08
    -collection
    0.08
     sightings
    0.08
    è©®
    0.08
    pagesize
    0.08
    Activations Density 0.005%

    No Known Activations